summaryrefslogtreecommitdiff
path: root/include
diff options
context:
space:
mode:
Diffstat (limited to 'include')
-rw-r--r--include/linux/bitmap.h95
-rw-r--r--include/linux/bitops.h23
-rw-r--r--include/linux/cpumask.h2
-rw-r--r--include/linux/linkmode.h27
-rw-r--r--include/linux/netdevice.h7
-rw-r--r--include/net/dst_metadata.h10
-rw-r--r--include/net/flow_dissector.h2
-rw-r--r--include/net/gre.h70
-rw-r--r--include/net/ip6_tunnel.h4
-rw-r--r--include/net/ip_tunnels.h139
-rw-r--r--include/net/pfcp.h90
-rw-r--r--include/net/udp_tunnel.h4
-rw-r--r--include/uapi/linux/if_tunnel.h36
-rw-r--r--include/uapi/linux/pkt_cls.h14
14 files changed, 392 insertions, 131 deletions
diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index aa4096126553..8c4768c44a01 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -83,6 +83,10 @@ struct device;
* bitmap_to_arr64(buf, src, nbits) Copy nbits from buf to u64[] dst
* bitmap_get_value8(map, start) Get 8bit value from map at start
* bitmap_set_value8(map, value, start) Set 8bit value to map at start
+ * bitmap_read(map, start, nbits) Read an nbits-sized value from
+ * map at start
+ * bitmap_write(map, value, start, nbits) Write an nbits-sized value to
+ * map at start
*
* Note, bitmap_zero() and bitmap_fill() operate over the region of
* unsigned longs, that is, bits behind bitmap till the unsigned long
@@ -222,9 +226,11 @@ void bitmap_fold(unsigned long *dst, const unsigned long *orig,
#define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1)))
#define BITMAP_LAST_WORD_MASK(nbits) (~0UL >> (-(nbits) & (BITS_PER_LONG - 1)))
+#define bitmap_size(nbits) (ALIGN(nbits, BITS_PER_LONG) / BITS_PER_BYTE)
+
static inline void bitmap_zero(unsigned long *dst, unsigned int nbits)
{
- unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
+ unsigned int len = bitmap_size(nbits);
if (small_const_nbits(nbits))
*dst = 0;
@@ -234,7 +240,7 @@ static inline void bitmap_zero(unsigned long *dst, unsigned int nbits)
static inline void bitmap_fill(unsigned long *dst, unsigned int nbits)
{
- unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
+ unsigned int len = bitmap_size(nbits);
if (small_const_nbits(nbits))
*dst = ~0UL;
@@ -245,7 +251,7 @@ static inline void bitmap_fill(unsigned long *dst, unsigned int nbits)
static inline void bitmap_copy(unsigned long *dst, const unsigned long *src,
unsigned int nbits)
{
- unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
+ unsigned int len = bitmap_size(nbits);
if (small_const_nbits(nbits))
*dst = *src;
@@ -722,38 +728,83 @@ static inline void bitmap_from_u64(unsigned long *dst, u64 mask)
}
/**
- * bitmap_get_value8 - get an 8-bit value within a memory region
+ * bitmap_read - read a value of n-bits from the memory region
* @map: address to the bitmap memory region
- * @start: bit offset of the 8-bit value; must be a multiple of 8
+ * @start: bit offset of the n-bit value
+ * @nbits: size of value in bits, nonzero, up to BITS_PER_LONG
*
- * Returns the 8-bit value located at the @start bit offset within the @src
- * memory region.
+ * Returns: value of @nbits bits located at the @start bit offset within the
+ * @map memory region. For @nbits = 0 and @nbits > BITS_PER_LONG the return
+ * value is undefined.
*/
-static inline unsigned long bitmap_get_value8(const unsigned long *map,
- unsigned long start)
+static inline unsigned long bitmap_read(const unsigned long *map,
+ unsigned long start,
+ unsigned long nbits)
{
- const size_t index = BIT_WORD(start);
- const unsigned long offset = start % BITS_PER_LONG;
+ size_t index = BIT_WORD(start);
+ unsigned long offset = start % BITS_PER_LONG;
+ unsigned long space = BITS_PER_LONG - offset;
+ unsigned long value_low, value_high;
+
+ if (unlikely(!nbits || nbits > BITS_PER_LONG))
+ return 0;
+
+ if (space >= nbits)
+ return (map[index] >> offset) & BITMAP_LAST_WORD_MASK(nbits);
- return (map[index] >> offset) & 0xFF;
+ value_low = map[index] & BITMAP_FIRST_WORD_MASK(start);
+ value_high = map[index + 1] & BITMAP_LAST_WORD_MASK(start + nbits);
+ return (value_low >> offset) | (value_high << space);
}
/**
- * bitmap_set_value8 - set an 8-bit value within a memory region
+ * bitmap_write - write n-bit value within a memory region
* @map: address to the bitmap memory region
- * @value: the 8-bit value; values wider than 8 bits may clobber bitmap
- * @start: bit offset of the 8-bit value; must be a multiple of 8
+ * @value: value to write, clamped to nbits
+ * @start: bit offset of the n-bit value
+ * @nbits: size of value in bits, nonzero, up to BITS_PER_LONG.
+ *
+ * bitmap_write() behaves as-if implemented as @nbits calls of __assign_bit(),
+ * i.e. bits beyond @nbits are ignored:
+ *
+ * for (bit = 0; bit < nbits; bit++)
+ * __assign_bit(start + bit, bitmap, val & BIT(bit));
+ *
+ * For @nbits == 0 and @nbits > BITS_PER_LONG no writes are performed.
*/
-static inline void bitmap_set_value8(unsigned long *map, unsigned long value,
- unsigned long start)
-{
- const size_t index = BIT_WORD(start);
- const unsigned long offset = start % BITS_PER_LONG;
-
- map[index] &= ~(0xFFUL << offset);
+static inline void bitmap_write(unsigned long *map, unsigned long value,
+ unsigned long start, unsigned long nbits)
+{
+ size_t index;
+ unsigned long offset;
+ unsigned long space;
+ unsigned long mask;
+ bool fit;
+
+ if (unlikely(!nbits || nbits > BITS_PER_LONG))
+ return;
+
+ mask = BITMAP_LAST_WORD_MASK(nbits);
+ value &= mask;
+ offset = start % BITS_PER_LONG;
+ space = BITS_PER_LONG - offset;
+ fit = space >= nbits;
+ index = BIT_WORD(start);
+
+ map[index] &= (fit ? (~(mask << offset)) : ~BITMAP_FIRST_WORD_MASK(start));
map[index] |= value << offset;
+ if (fit)
+ return;
+
+ map[index + 1] &= BITMAP_FIRST_WORD_MASK(start + nbits);
+ map[index + 1] |= (value >> space);
}
+#define bitmap_get_value8(map, start) \
+ bitmap_read(map, start, BITS_PER_BYTE)
+#define bitmap_set_value8(map, value, start) \
+ bitmap_write(map, value, start, BITS_PER_BYTE)
+
#endif /* __ASSEMBLY__ */
#endif /* __LINUX_BITMAP_H */
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index 2ba557e067fe..b25dc8742124 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -21,6 +21,8 @@
#define BITS_TO_U32(nr) __KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(u32))
#define BITS_TO_BYTES(nr) __KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(char))
+#define BYTES_TO_BITS(nb) ((nb) * BITS_PER_BYTE)
+
extern unsigned int __sw_hweight8(unsigned int w);
extern unsigned int __sw_hweight16(unsigned int w);
extern unsigned int __sw_hweight32(unsigned int w);
@@ -80,6 +82,7 @@ __check_bitop_pr(__test_and_set_bit);
__check_bitop_pr(__test_and_clear_bit);
__check_bitop_pr(__test_and_change_bit);
__check_bitop_pr(test_bit);
+__check_bitop_pr(test_bit_acquire);
#undef __check_bitop_pr
@@ -272,23 +275,11 @@ static inline unsigned long fns(unsigned long word, unsigned int n)
* @addr: the address to start counting from
* @value: the value to assign
*/
-static __always_inline void assign_bit(long nr, volatile unsigned long *addr,
- bool value)
-{
- if (value)
- set_bit(nr, addr);
- else
- clear_bit(nr, addr);
-}
+#define assign_bit(nr, addr, value) \
+ ((value) ? set_bit((nr), (addr)) : clear_bit((nr), (addr)))
-static __always_inline void __assign_bit(long nr, volatile unsigned long *addr,
- bool value)
-{
- if (value)
- __set_bit(nr, addr);
- else
- __clear_bit(nr, addr);
-}
+#define __assign_bit(nr, addr, value) \
+ ((value) ? __set_bit((nr), (addr)) : __clear_bit((nr), (addr)))
/**
* __ptr_set_bit - Set bit in a pointer's value
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 1c29947db848..6519f9c77709 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -853,7 +853,7 @@ static inline int cpulist_parse(const char *buf, struct cpumask *dstp)
*/
static inline unsigned int cpumask_size(void)
{
- return BITS_TO_LONGS(large_cpumask_bits) * sizeof(long);
+ return bitmap_size(large_cpumask_bits);
}
/*
diff --git a/include/linux/linkmode.h b/include/linux/linkmode.h
index 287f590ed56b..d94bfd9ac8cc 100644
--- a/include/linux/linkmode.h
+++ b/include/linux/linkmode.h
@@ -43,29 +43,10 @@ static inline int linkmode_andnot(unsigned long *dst, const unsigned long *src1,
return bitmap_andnot(dst, src1, src2, __ETHTOOL_LINK_MODE_MASK_NBITS);
}
-static inline void linkmode_set_bit(int nr, volatile unsigned long *addr)
-{
- __set_bit(nr, addr);
-}
-
-static inline void linkmode_clear_bit(int nr, volatile unsigned long *addr)
-{
- __clear_bit(nr, addr);
-}
-
-static inline void linkmode_mod_bit(int nr, volatile unsigned long *addr,
- int set)
-{
- if (set)
- linkmode_set_bit(nr, addr);
- else
- linkmode_clear_bit(nr, addr);
-}
-
-static inline int linkmode_test_bit(int nr, const volatile unsigned long *addr)
-{
- return test_bit(nr, addr);
-}
+#define linkmode_test_bit test_bit
+#define linkmode_set_bit __set_bit
+#define linkmode_clear_bit __clear_bit
+#define linkmode_mod_bit __assign_bit
static inline void linkmode_set_bit_array(const int *array, int array_size,
unsigned long *addr)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index e41d30ebaca6..55c7cf9404a4 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -59,7 +59,7 @@ struct ethtool_ops;
struct kernel_hwtstamp_config;
struct phy_device;
struct dsa_port;
-struct ip_tunnel_parm;
+struct ip_tunnel_parm_kern;
struct macsec_context;
struct macsec_ops;
struct netdev_name_node;
@@ -1327,7 +1327,7 @@ struct netdev_net_notifier {
* queue id bound to an AF_XDP socket. The flags field specifies if
* only RX, only Tx, or both should be woken up using the flags
* XDP_WAKEUP_RX and XDP_WAKEUP_TX.
- * int (*ndo_tunnel_ctl)(struct net_device *dev, struct ip_tunnel_parm *p,
+ * int (*ndo_tunnel_ctl)(struct net_device *dev, struct ip_tunnel_parm_kern *p,
* int cmd);
* Add, change, delete or get information on an IPv4 tunnel.
* struct net_device *(*ndo_get_peer_dev)(struct net_device *dev);
@@ -1583,7 +1583,8 @@ struct net_device_ops {
int (*ndo_xsk_wakeup)(struct net_device *dev,
u32 queue_id, u32 flags);
int (*ndo_tunnel_ctl)(struct net_device *dev,
- struct ip_tunnel_parm *p, int cmd);
+ struct ip_tunnel_parm_kern *p,
+ int cmd);
struct net_device * (*ndo_get_peer_dev)(struct net_device *dev);
int (*ndo_fill_forward_path)(struct net_device_path_ctx *ctx,
struct net_device_path *path);
diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h
index 1b7fae4c6b24..4160731dcb6e 100644
--- a/include/net/dst_metadata.h
+++ b/include/net/dst_metadata.h
@@ -198,7 +198,7 @@ static inline struct metadata_dst *__ip_tun_set_dst(__be32 saddr,
__be32 daddr,
__u8 tos, __u8 ttl,
__be16 tp_dst,
- __be16 flags,
+ const unsigned long *flags,
__be64 tunnel_id,
int md_size)
{
@@ -215,7 +215,7 @@ static inline struct metadata_dst *__ip_tun_set_dst(__be32 saddr,
}
static inline struct metadata_dst *ip_tun_rx_dst(struct sk_buff *skb,
- __be16 flags,
+ const unsigned long *flags,
__be64 tunnel_id,
int md_size)
{
@@ -230,7 +230,7 @@ static inline struct metadata_dst *__ipv6_tun_set_dst(const struct in6_addr *sad
__u8 tos, __u8 ttl,
__be16 tp_dst,
__be32 label,
- __be16 flags,
+ const unsigned long *flags,
__be64 tunnel_id,
int md_size)
{
@@ -243,7 +243,7 @@ static inline struct metadata_dst *__ipv6_tun_set_dst(const struct in6_addr *sad
info = &tun_dst->u.tun_info;
info->mode = IP_TUNNEL_INFO_IPV6;
- info->key.tun_flags = flags;
+ ip_tunnel_flags_copy(info->key.tun_flags, flags);
info->key.tun_id = tunnel_id;
info->key.tp_src = 0;
info->key.tp_dst = tp_dst;
@@ -259,7 +259,7 @@ static inline struct metadata_dst *__ipv6_tun_set_dst(const struct in6_addr *sad
}
static inline struct metadata_dst *ipv6_tun_rx_dst(struct sk_buff *skb,
- __be16 flags,
+ const unsigned long *flags,
__be64 tunnel_id,
int md_size)
{
diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h
index 1a7131d6cb0e..9ab376d1a677 100644
--- a/include/net/flow_dissector.h
+++ b/include/net/flow_dissector.h
@@ -97,7 +97,7 @@ struct flow_dissector_key_enc_opts {
* here but seems difficult to #include
*/
u8 len;
- __be16 dst_opt_type;
+ u32 dst_opt_type;
};
struct flow_dissector_key_keyid {
diff --git a/include/net/gre.h b/include/net/gre.h
index 4e209708b754..ccd293203284 100644
--- a/include/net/gre.h
+++ b/include/net/gre.h
@@ -49,67 +49,61 @@ static inline bool netif_is_ip6gretap(const struct net_device *dev)
!strcmp(dev->rtnl_link_ops->kind, "ip6gretap");
}
-static inline int gre_calc_hlen(__be16 o_flags)
+static inline int gre_calc_hlen(const unsigned long *o_flags)
{
int addend = 4;
- if (o_flags & TUNNEL_CSUM)
+ if (test_bit(IP_TUNNEL_CSUM_BIT, o_flags))
addend += 4;
- if (o_flags & TUNNEL_KEY)
+ if (test_bit(IP_TUNNEL_KEY_BIT, o_flags))
addend += 4;
- if (o_flags & TUNNEL_SEQ)
+ if (test_bit(IP_TUNNEL_SEQ_BIT, o_flags))
addend += 4;
return addend;
}
-static inline __be16 gre_flags_to_tnl_flags(__be16 flags)
+static inline void gre_flags_to_tnl_flags(unsigned long *dst, __be16 flags)
{
- __be16 tflags = 0;
-
- if (flags & GRE_CSUM)
- tflags |= TUNNEL_CSUM;
- if (flags & GRE_ROUTING)
- tflags |= TUNNEL_ROUTING;
- if (flags & GRE_KEY)
- tflags |= TUNNEL_KEY;
- if (flags & GRE_SEQ)
- tflags |= TUNNEL_SEQ;
- if (flags & GRE_STRICT)
- tflags |= TUNNEL_STRICT;
- if (flags & GRE_REC)
- tflags |= TUNNEL_REC;
- if (flags & GRE_VERSION)
- tflags |= TUNNEL_VERSION;
-
- return tflags;
+ IP_TUNNEL_DECLARE_FLAGS(res) = { };
+
+ __assign_bit(IP_TUNNEL_CSUM_BIT, res, flags & GRE_CSUM);
+ __assign_bit(IP_TUNNEL_ROUTING_BIT, res, flags & GRE_ROUTING);
+ __assign_bit(IP_TUNNEL_KEY_BIT, res, flags & GRE_KEY);
+ __assign_bit(IP_TUNNEL_SEQ_BIT, res, flags & GRE_SEQ);
+ __assign_bit(IP_TUNNEL_STRICT_BIT, res, flags & GRE_STRICT);
+ __assign_bit(IP_TUNNEL_REC_BIT, res, flags & GRE_REC);
+ __assign_bit(IP_TUNNEL_VERSION_BIT, res, flags & GRE_VERSION);
+
+ ip_tunnel_flags_copy(dst, res);
}
-static inline __be16 gre_tnl_flags_to_gre_flags(__be16 tflags)
+static inline __be16 gre_tnl_flags_to_gre_flags(const unsigned long *tflags)
{
__be16 flags = 0;
- if (tflags & TUNNEL_CSUM)
+ if (test_bit(IP_TUNNEL_CSUM_BIT, tflags))
flags |= GRE_CSUM;
- if (tflags & TUNNEL_ROUTING)
+ if (test_bit(IP_TUNNEL_ROUTING_BIT, tflags))
flags |= GRE_ROUTING;
- if (tflags & TUNNEL_KEY)
+ if (test_bit(IP_TUNNEL_KEY_BIT, tflags))
flags |= GRE_KEY;
- if (tflags & TUNNEL_SEQ)
+ if (test_bit(IP_TUNNEL_SEQ_BIT, tflags))
flags |= GRE_SEQ;
- if (tflags & TUNNEL_STRICT)
+ if (test_bit(IP_TUNNEL_STRICT_BIT, tflags))
flags |= GRE_STRICT;
- if (tflags & TUNNEL_REC)
+ if (test_bit(IP_TUNNEL_REC_BIT, tflags))
flags |= GRE_REC;
- if (tflags & TUNNEL_VERSION)
+ if (test_bit(IP_TUNNEL_VERSION_BIT, tflags))
flags |= GRE_VERSION;
return flags;
}
static inline void gre_build_header(struct sk_buff *skb, int hdr_len,
- __be16 flags, __be16 proto,
+ const unsigned long *flags, __be16 proto,
__be32 key, __be32 seq)
{
+ IP_TUNNEL_DECLARE_FLAGS(cond) = { };
struct gre_base_hdr *greh;
skb_push(skb, hdr_len);
@@ -120,18 +114,22 @@ static inline void gre_build_header(struct sk_buff *skb, int hdr_len,
greh->flags = gre_tnl_flags_to_gre_flags(flags);
greh->protocol = proto;
- if (flags & (TUNNEL_KEY | TUNNEL_CSUM | TUNNEL_SEQ)) {
+ __set_bit(IP_TUNNEL_KEY_BIT, cond);
+ __set_bit(IP_TUNNEL_CSUM_BIT, cond);
+ __set_bit(IP_TUNNEL_SEQ_BIT, cond);
+
+ if (ip_tunnel_flags_intersect(flags, cond)) {
__be32 *ptr = (__be32 *)(((u8 *)greh) + hdr_len - 4);
- if (flags & TUNNEL_SEQ) {
+ if (test_bit(IP_TUNNEL_SEQ_BIT, flags)) {
*ptr = seq;
ptr--;
}
- if (flags & TUNNEL_KEY) {
+ if (test_bit(IP_TUNNEL_KEY_BIT, flags)) {
*ptr = key;
ptr--;
}
- if (flags & TUNNEL_CSUM &&
+ if (test_bit(IP_TUNNEL_CSUM_BIT, flags) &&
!(skb_shinfo(skb)->gso_type &
(SKB_GSO_GRE | SKB_GSO_GRE_CSUM))) {
*ptr = 0;
diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h
index 74b369bddf49..399592405c72 100644
--- a/include/net/ip6_tunnel.h
+++ b/include/net/ip6_tunnel.h
@@ -30,8 +30,8 @@ struct __ip6_tnl_parm {
struct in6_addr laddr; /* local tunnel end-point address */
struct in6_addr raddr; /* remote tunnel end-point address */
- __be16 i_flags;
- __be16 o_flags;
+ IP_TUNNEL_DECLARE_FLAGS(i_flags);
+ IP_TUNNEL_DECLARE_FLAGS(o_flags);
__be32 i_key;
__be32 o_key;
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index 5cd64bb2104d..d8f574fbb11e 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -36,6 +36,24 @@
(sizeof_field(struct ip_tunnel_key, u) - \
sizeof_field(struct ip_tunnel_key, u.ipv4))
+#define __ipt_flag_op(op, ...) \
+ op(__VA_ARGS__, __IP_TUNNEL_FLAG_NUM)
+
+#define IP_TUNNEL_DECLARE_FLAGS(...) \
+ __ipt_flag_op(DECLARE_BITMAP, __VA_ARGS__)
+
+#define ip_tunnel_flags_zero(...) __ipt_flag_op(bitmap_zero, __VA_ARGS__)
+#define ip_tunnel_flags_copy(...) __ipt_flag_op(bitmap_copy, __VA_ARGS__)
+#define ip_tunnel_flags_and(...) __ipt_flag_op(bitmap_and, __VA_ARGS__)
+#define ip_tunnel_flags_or(...) __ipt_flag_op(bitmap_or, __VA_ARGS__)
+
+#define ip_tunnel_flags_empty(...) \
+ __ipt_flag_op(bitmap_empty, __VA_ARGS__)
+#define ip_tunnel_flags_intersect(...) \
+ __ipt_flag_op(bitmap_intersects, __VA_ARGS__)
+#define ip_tunnel_flags_subset(...) \
+ __ipt_flag_op(bitmap_subset, __VA_ARGS__)
+
struct ip_tunnel_key {
__be64 tun_id;
union {
@@ -48,11 +66,11 @@ struct ip_tunnel_key {
struct in6_addr dst;
} ipv6;
} u;
- __be16 tun_flags;
- u8 tos; /* TOS for IPv4, TC for IPv6 */
- u8 ttl; /* TTL for IPv4, HL for IPv6 */
+ IP_TUNNEL_DECLARE_FLAGS(tun_flags);
__be32 label; /* Flow Label for IPv6 */
u32 nhid;
+ u8 tos; /* TOS for IPv4, TC for IPv6 */
+ u8 ttl; /* TTL for IPv4, HL for IPv6 */
__be16 tp_src;
__be16 tp_dst;
__u8 flow_flags;
@@ -110,6 +128,17 @@ struct ip_tunnel_prl_entry {
struct metadata_dst;
+/* Kernel-side variant of ip_tunnel_parm */
+struct ip_tunnel_parm_kern {
+ char name[IFNAMSIZ];
+ IP_TUNNEL_DECLARE_FLAGS(i_flags);
+ IP_TUNNEL_DECLARE_FLAGS(o_flags);
+ __be32 i_key;
+ __be32 o_key;
+ int link;
+ struct iphdr iph;
+};
+
struct ip_tunnel {
struct ip_tunnel __rcu *next;
struct hlist_node hash_node;
@@ -136,7 +165,7 @@ struct ip_tunnel {
struct dst_cache dst_cache;
- struct ip_tunnel_parm parms;
+ struct ip_tunnel_parm_kern parms;
int mlink;
int encap_hlen; /* Encap header length (FOU,GUE) */
@@ -157,7 +186,7 @@ struct ip_tunnel {
};
struct tnl_ptk_info {
- __be16 flags;
+ IP_TUNNEL_DECLARE_FLAGS(flags);
__be16 proto;
__be32 key;
__be32 seq;
@@ -179,11 +208,80 @@ struct ip_tunnel_net {
int type;
};
+static inline void ip_tunnel_set_options_present(unsigned long *flags)
+{
+ IP_TUNNEL_DECLARE_FLAGS(present) = { };
+
+ __set_bit(IP_TUNNEL_GENEVE_OPT_BIT, present);
+ __set_bit(IP_TUNNEL_VXLAN_OPT_BIT, present);
+ __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, present);
+ __set_bit(IP_TUNNEL_GTP_OPT_BIT, present);
+ __set_bit(IP_TUNNEL_PFCP_OPT_BIT, present);
+
+ ip_tunnel_flags_or(flags, flags, present);
+}
+
+static inline void ip_tunnel_clear_options_present(unsigned long *flags)
+{
+ IP_TUNNEL_DECLARE_FLAGS(present) = { };
+
+ __set_bit(IP_TUNNEL_GENEVE_OPT_BIT, present);
+ __set_bit(IP_TUNNEL_VXLAN_OPT_BIT, present);
+ __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, present);
+ __set_bit(IP_TUNNEL_GTP_OPT_BIT, present);
+ __set_bit(IP_TUNNEL_PFCP_OPT_BIT, present);
+
+ __ipt_flag_op(bitmap_andnot, flags, flags, present);
+}
+
+static inline bool ip_tunnel_is_options_present(const unsigned long *flags)
+{
+ IP_TUNNEL_DECLARE_FLAGS(present) = { };
+
+ __set_bit(IP_TUNNEL_GENEVE_OPT_BIT, present);
+ __set_bit(IP_TUNNEL_VXLAN_OPT_BIT, present);
+ __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, present);
+ __set_bit(IP_TUNNEL_GTP_OPT_BIT, present);
+ __set_bit(IP_TUNNEL_PFCP_OPT_BIT, present);
+
+ return ip_tunnel_flags_intersect(flags, present);
+}
+
+static inline bool ip_tunnel_flags_is_be16_compat(const unsigned long *flags)
+{
+ IP_TUNNEL_DECLARE_FLAGS(supp) = { };
+
+ bitmap_set(supp, 0, BITS_PER_TYPE(__be16));
+ __set_bit(IP_TUNNEL_VTI_BIT, supp);
+
+ return ip_tunnel_flags_subset(flags, supp);
+}
+
+static inline void ip_tunnel_flags_from_be16(unsigned long *dst, __be16 flags)
+{
+ ip_tunnel_flags_zero(dst);
+
+ bitmap_write(dst, be16_to_cpu(flags), 0, BITS_PER_TYPE(__be16));
+ __assign_bit(IP_TUNNEL_VTI_BIT, dst, flags & VTI_ISVTI);
+}
+
+static inline __be16 ip_tunnel_flags_to_be16(const unsigned long *flags)
+{
+ __be16 ret;
+
+ ret = cpu_to_be16(bitmap_read(flags, 0, BITS_PER_TYPE(__be16)));
+ if (test_bit(IP_TUNNEL_VTI_BIT, flags))
+ ret |= VTI_ISVTI;
+
+ return ret;
+}
+
static inline void ip_tunnel_key_init(struct ip_tunnel_key *key,
__be32 saddr, __be32 daddr,
u8 tos, u8 ttl, __be32 label,
__be16 tp_src, __be16 tp_dst,
- __be64 tun_id, __be16 tun_flags)
+ __be64 tun_id,
+ const unsigned long *tun_flags)
{
key->tun_id = tun_id;
key->u.ipv4.src = saddr;
@@ -193,7 +291,7 @@ static inline void ip_tunnel_key_init(struct ip_tunnel_key *key,
key->tos = tos;
key->ttl = ttl;
key->label = label;
- key->tun_flags = tun_flags;
+ ip_tunnel_flags_copy(key->tun_flags, tun_flags);
/* For the tunnel types on the top of IPsec, the tp_src and tp_dst of
* the upper tunnel are used.
@@ -214,12 +312,8 @@ ip_tunnel_dst_cache_usable(const struct sk_buff *skb,
{
if (skb->mark)
return false;
- if (!info)
- return true;
- if (info->key.tun_flags & TUNNEL_NOCACHE)
- return false;
- return true;
+ return !info || !test_bit(IP_TUNNEL_NOCACHE_BIT, info->key.tun_flags);
}
static inline unsigned short ip_tunnel_info_af(const struct ip_tunnel_info
@@ -291,14 +385,18 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
const struct iphdr *tnl_params, const u8 protocol);
void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
const u8 proto, int tunnel_hlen);
-int ip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd);
+int ip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm_kern *p,
+ int cmd);
+bool ip_tunnel_parm_from_user(struct ip_tunnel_parm_kern *kp,
+ const void __user *data);
+bool ip_tunnel_parm_to_user(void __user *data, struct ip_tunnel_parm_kern *kp);
int ip_tunnel_siocdevprivate(struct net_device *dev, struct ifreq *ifr,
void __user *data, int cmd);
int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict);
int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu);
struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
- int link, __be16 flags,
+ int link, const unsigned long *flags,
__be32 remote, __be32 local,
__be32 key);
@@ -307,16 +405,16 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
const struct tnl_ptk_info *tpi, struct metadata_dst *tun_dst,
bool log_ecn_error);
int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[],
- struct ip_tunnel_parm *p, __u32 fwmark);
+ struct ip_tunnel_parm_kern *p, __u32 fwmark);
int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
- struct ip_tunnel_parm *p, __u32 fwmark);
+ struct ip_tunnel_parm_kern *p, __u32 fwmark);
void ip_tunnel_setup(struct net_device *dev, unsigned int net_id);
bool ip_tunnel_netlink_encap_parms(struct nlattr *data[],
struct ip_tunnel_encap *encap);
void ip_tunnel_netlink_parms(struct nlattr *data[],
- struct ip_tunnel_parm *parms);
+ struct ip_tunnel_parm_kern *parms);
extern const struct header_ops ip_tunnel_header_ops;
__be16 ip_tunnel_parse_protocol(const struct sk_buff *skb);
@@ -514,12 +612,13 @@ static inline void ip_tunnel_info_opts_get(void *to,
static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info,
const void *from, int len,
- __be16 flags)
+ const unsigned long *flags)
{
info->options_len = len;
if (len > 0) {
memcpy(ip_tunnel_info_opts(info), from, len);
- info->key.tun_flags |= flags;
+ ip_tunnel_flags_or(info->key.tun_flags, info->key.tun_flags,
+ flags);
}
}
@@ -563,7 +662,7 @@ static inline void ip_tunnel_info_opts_get(void *to,
static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info,
const void *from, int len,
- __be16 flags)
+ const unsigned long *flags)
{
info->options_len = 0;
}
diff --git a/include/net/pfcp.h b/include/net/pfcp.h
new file mode 100644
index 000000000000..af14f970b80e
--- /dev/null
+++ b/include/net/pfcp.h
@@ -0,0 +1,90 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _PFCP_H_
+#define _PFCP_H_
+
+#include <uapi/linux/if_ether.h>
+#include <net/dst_metadata.h>
+#include <linux/netdevice.h>
+#include <uapi/linux/ipv6.h>
+#include <net/udp_tunnel.h>
+#include <uapi/linux/udp.h>
+#include <uapi/linux/ip.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/bits.h>
+
+#define PFCP_PORT 8805
+
+/* PFCP protocol header */
+struct pfcphdr {
+ u8 flags;
+ u8 message_type;
+ __be16 message_length;
+};
+
+/* PFCP header flags */
+#define PFCP_SEID_FLAG BIT(0)
+#define PFCP_MP_FLAG BIT(1)
+
+#define PFCP_VERSION_MASK GENMASK(4, 0)
+
+#define PFCP_HLEN (sizeof(struct udphdr) + sizeof(struct pfcphdr))
+
+/* PFCP node related messages */
+struct pfcphdr_node {
+ u8 seq_number[3];
+ u8 reserved;
+};
+
+/* PFCP session related messages */
+struct pfcphdr_session {
+ __be64 seid;
+ u8 seq_number[3];
+#ifdef __LITTLE_ENDIAN_BITFIELD
+ u8 message_priority:4,
+ reserved:4;
+#elif defined(__BIG_ENDIAN_BITFIELD)
+ u8 reserved:4,
+ message_priprity:4;
+#else
+#error "Please fix <asm/byteorder>"
+#endif
+};
+
+struct pfcp_metadata {
+ u8 type;
+ __be64 seid;
+} __packed;
+
+enum {
+ PFCP_TYPE_NODE = 0,
+ PFCP_TYPE_SESSION = 1,
+};
+
+#define PFCP_HEADROOM (sizeof(struct iphdr) + sizeof(struct udphdr) + \
+ sizeof(struct pfcphdr) + sizeof(struct ethhdr))
+#define PFCP6_HEADROOM (sizeof(struct ipv6hdr) + sizeof(struct udphdr) + \
+ sizeof(struct pfcphdr) + sizeof(struct ethhdr))
+
+static inline struct pfcphdr *pfcp_hdr(struct sk_buff *skb)
+{
+ return (struct pfcphdr *)(udp_hdr(skb) + 1);
+}
+
+static inline struct pfcphdr_node *pfcp_hdr_node(struct sk_buff *skb)
+{
+ return (struct pfcphdr_node *)(pfcp_hdr(skb) + 1);
+}
+
+static inline struct pfcphdr_session *pfcp_hdr_session(struct sk_buff *skb)
+{
+ return (struct pfcphdr_session *)(pfcp_hdr(skb) + 1);
+}
+
+static inline bool netif_is_pfcp(const struct net_device *dev)
+{
+ return dev->rtnl_link_ops &&
+ !strcmp(dev->rtnl_link_ops->kind, "pfcp");
+}
+
+#endif
diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h
index d716214fe03d..a93dc51f6323 100644
--- a/include/net/udp_tunnel.h
+++ b/include/net/udp_tunnel.h
@@ -179,8 +179,8 @@ struct dst_entry *udp_tunnel6_dst_lookup(struct sk_buff *skb,
struct dst_cache *dst_cache);
struct metadata_dst *udp_tun_rx_dst(struct sk_buff *skb, unsigned short family,
- __be16 flags, __be64 tunnel_id,
- int md_size);
+ const unsigned long *flags,
+ __be64 tunnel_id, int md_size);
#ifdef CONFIG_INET
static inline int udp_tunnel_handle_offloads(struct sk_buff *skb, bool udp_csum)
diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h
index 102119628ff5..e1a246dd8c62 100644
--- a/include/uapi/linux/if_tunnel.h
+++ b/include/uapi/linux/if_tunnel.h
@@ -161,6 +161,14 @@ enum {
#define IFLA_VTI_MAX (__IFLA_VTI_MAX - 1)
+#ifndef __KERNEL__
+/* Historically, tunnel flags have been defined as __be16 and now there are
+ * no free bits left. It is strongly advised to switch the already existing
+ * userspace code to the new *_BIT definitions from down below, as __be16
+ * can't be simply cast to a wider type on LE systems. All new flags and
+ * code must use *_BIT only.
+ */
+
#define TUNNEL_CSUM __cpu_to_be16(0x01)
#define TUNNEL_ROUTING __cpu_to_be16(0x02)
#define TUNNEL_KEY __cpu_to_be16(0x04)
@@ -181,5 +189,33 @@ enum {
#define TUNNEL_OPTIONS_PRESENT \
(TUNNEL_GENEVE_OPT | TUNNEL_VXLAN_OPT | TUNNEL_ERSPAN_OPT | \
TUNNEL_GTP_OPT)
+#endif
+
+enum {
+ IP_TUNNEL_CSUM_BIT = 0U,
+ IP_TUNNEL_ROUTING_BIT,
+ IP_TUNNEL_KEY_BIT,
+ IP_TUNNEL_SEQ_BIT,
+ IP_TUNNEL_STRICT_BIT,
+ IP_TUNNEL_REC_BIT,
+ IP_TUNNEL_VERSION_BIT,
+ IP_TUNNEL_NO_KEY_BIT,
+ IP_TUNNEL_DONT_FRAGMENT_BIT,
+ IP_TUNNEL_OAM_BIT,
+ IP_TUNNEL_CRIT_OPT_BIT,
+ IP_TUNNEL_GENEVE_OPT_BIT, /* OPTIONS_PRESENT */
+ IP_TUNNEL_VXLAN_OPT_BIT, /* OPTIONS_PRESENT */
+ IP_TUNNEL_NOCACHE_BIT,
+ IP_TUNNEL_ERSPAN_OPT_BIT, /* OPTIONS_PRESENT */
+ IP_TUNNEL_GTP_OPT_BIT, /* OPTIONS_PRESENT */
+
+ IP_TUNNEL_VTI_BIT,
+ IP_TUNNEL_SIT_ISATAP_BIT = IP_TUNNEL_VTI_BIT,
+
+ /* Flags starting from here are not available via the old UAPI */
+ IP_TUNNEL_PFCP_OPT_BIT, /* OPTIONS_PRESENT */
+
+ __IP_TUNNEL_FLAG_NUM,
+};
#endif /* _UAPI_IF_TUNNEL_H_ */
diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h
index ea277039f89d..229fc925ec3a 100644
--- a/include/uapi/linux/pkt_cls.h
+++ b/include/uapi/linux/pkt_cls.h
@@ -587,6 +587,10 @@ enum {
* TCA_FLOWER_KEY_ENC_OPT_GTP_
* attributes
*/
+ TCA_FLOWER_KEY_ENC_OPTS_PFCP, /* Nested
+ * TCA_FLOWER_KEY_ENC_IPT_PFCP
+ * attributes
+ */
__TCA_FLOWER_KEY_ENC_OPTS_MAX,
};
@@ -637,6 +641,16 @@ enum {
(__TCA_FLOWER_KEY_ENC_OPT_GTP_MAX - 1)
enum {
+ TCA_FLOWER_KEY_ENC_OPT_PFCP_UNSPEC,
+ TCA_FLOWER_KEY_ENC_OPT_PFCP_TYPE, /* u8 */
+ TCA_FLOWER_KEY_ENC_OPT_PFCP_SEID, /* be64 */
+ __TCA_FLOWER_KEY_ENC_OPT_PFCP_MAX,
+};
+
+#define TCA_FLOWER_KEY_ENC_OPT_PFCP_MAX \
+ (__TCA_FLOWER_KEY_ENC_OPT_PFCP_MAX - 1)
+
+enum {
TCA_FLOWER_KEY_MPLS_OPTS_UNSPEC,
TCA_FLOWER_KEY_MPLS_OPTS_LSE,
__TCA_FLOWER_KEY_MPLS_OPTS_MAX,
generated by cgit v1.2.3 (git 2.0.4) at 2026-02-14 17:23:56 +0000